计算机科学 ›› 2017, Vol. 44 ›› Issue (12): 279-282.doi: 10.11896/j.issn.1002-137X.2017.12.050

• 图形图像与模式识别 • 上一篇    下一篇

基于尺寸建立个性化人体模型的方法

高一荻,蒋夏军,施慧彬   

  1. 南京航空航天大学计算机科学与技术学院 南京211100,南京航空航天大学计算机科学与技术学院 南京211100,南京航空航天大学计算机科学与技术学院 南京211100
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受江苏省自然科学基金(BK20140826)资助

Personalized Human Body Modeling Method Based on Measurements

GAO Yi-di, JIANG Xia-jun and SHI Hui-bin   

  • Online:2018-12-01 Published:2018-12-01

摘要: 近年来,人体模型定制已成为计算机图形学领域的重要研究课题之一。文中提出一种基于少量人体尺寸生成个性化人体模型的方法——分块优化法。首先,根据MPI人体扫描模型数据库获得人体外形形变参数与尺寸参数,采用线性相关分析方法实现由若干尺寸恢复完整人体尺寸集。其次,通过参数优化的线性回归方法分析各部位三维人体外形参数与二维尺寸数据之间的关系,并根据输入尺寸对人体模型进行进一步精调。实验表明,上述方法能够生成准确反映人体外形的人体模型。

关键词: 三维人体模型,人体测量学,线性回归,参数优化

Abstract: In recent years,human body modeling has become an important task in the field of computer graphics.This paper proposed a new modeling method called optimistic segmentation method to generate 3D human body models from some anthropometric measurements.Firstly,according to the MPI scanned human body model database,the human body shape deformation parameters and measurement parameters are obtained,and the linear correlation analysis method is used to estimate the full human body measurement set.Secondly,the relationship between the 3D human body shape and the 2D measurement data is analyzed by the linear regression method,and the human body model is further refined according to the input measurements.The results of the experiment show that this method can generate a human body model which can accurately reflect the appearance of the human body.

Key words: 3D human body model,Anthropometry,Linear regression,Parameter optimization

[1] SEO H,CORDIER F,PHILIPPON L,et al.Interactive modelling of mpeg-4 deformable human body models[M]∥Defor-mable Avatars.Springer US,2001:120-131.
[2] SEO H,MAGNENEAT-THALMANN N.An automatic mode-ling of human bodies from sizing parameters[C]∥Proceedings of the 2003 Symposium on Interactive 3D Graphics.ACM,2003:19-26.
[3] SEO H,MAGNENEAT-THALMANN N.An example-basedapproach to human body manipulation[J].Graphical Models,2004,66(1):1-23.
[4] DENG W Y.Research on Method of 3D Personalized HumanBody Modeling Based on Photos and Neural Network[D].Hang-zhou:Zhejiang University,2008.(in Chinese) 邓卫燕.基于用户照片和神经网络的三维个性化人体建模方法研究[D].杭州:浙江大学,2008.
[5] ZHU S,MOK P Y,KWOK Y L.An efficient human model customization method based on orthogonal-view monocular photos[J].Computer-Aided Design,2013,45(11):1314-1332.
[6] ANGUELOV D,SRINIVASAN P,KOLLER D,et al.SCAPE:shape completion and animation of people[J].ACM Transactions on Graphics,2005,24(3):408-416.
[7] HASLER N,STOLL C,SUNKEL M,et al.A statistical model of human pose and body shape[J].Computer Graphics Forum.Blackwell Publishing Ltd,2009,28(2):337-346.
[8] KOO B Y,PARK E J,CHOI D K,et al.Example-based statistical framework for parametric modeling of human body shapes[J].Computers in Industry,2015,73:23-38.
[9] ZHANG Y,ZHENG J,MAGNENEAT-THALMANN N.Ex-ample-guided anthropometric human body modeling[J].The Visual Computer,2015,31(12):1615-1631.
[10] LAI J,WANG B,FU Q,et al.Automatic extraction method of human body sizes based on 3D point clouds[J].Journal of Central South University (Science and Technology),2014(8):2676-2683.(in Chinese) 赖军,王博,付全,等.基于点云模型的人体尺寸自动提取方法[J].中南大学学报(自然科学版),2014(8):2676-2683.
[11] YONG Y,WANG Z,XIA S,et al.Pose-Independent Joint Extraction from Scanned Human Body[J].Journal of Computer Research & Development,2008,45(7):1249-1258.
[12] CHEN G D,LI J W,PAN L,et al.Algorithm for ExtractingSkeleton of 3D Human Body Model Based on Body Characteristic[J].Computer Science,2009,6(7):295-297.(in Chinese) 陈国栋,李建微,潘林,等.基于人体特征三维人体模型的骨架提取算法[J].计算机科学,2009,36(7):295-297.
[13] SALZMANN M,EK C H,URTASUN R,et al.FactorizedOrthogonal Latent Spaces[J].Journal of Machine Learning Research,2010,9:701-708.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!